Abstract
The visualization of continuous multi-dimensional data based on their projection to a 2-dimensional space is a way to detect visually interesting patterns, as far as the projection provides a faithful image of the original data. In order to evaluate this faithfulness, we propose to visualize any measure associated to the data by coloring the corresponding Voronoï cells in the projection space, and we define specific measures. We experiment these techniques with the Principal Component Analysis and the Curvilinear Component Analysis applied to artificial and real databases.
Translated title of the contribution | Measuring and visualizing the distortions in the techniques of continuous projection |
---|---|
Original language | French |
Pages (from-to) | 443-472 |
Number of pages | 30 |
Journal | Revue d'Intelligence Artificielle |
Volume | 22 |
Issue number | 3-4 |
DOIs | |
Publication status | Published - 2008 |
Externally published | Yes |
Keywords
- Continuous projection
- Delaunay graph
- Distortion visualization
- Exploratory data analysis
- High-dimensional data
- Topology recovering
- Uncertainty visualization
- Voronoï cells